Skip to main content
Glama

Gleif Lei Screen

gleif_lei_screen
Read-onlyIdempotent

Bulk screen of LEI registrations in a jurisdiction across all ~3.4M LEIs in the GLEIF golden copy. Filter by registration status (LAPSED, RETIRED, ANNULLED, ISSUED ...), entity status, category, most recent legal-entity event (MERGERS_AND_ACQUISITIONS, ABSORPTION, DISSOLUTION, LIQUIDATION, CHANGE_LEGAL_NAME ...), a name fragment, and a lookback window in days. Answers "which LEIs in Germany lapsed in the last 30 days", "Delaware entities retired this quarter", "UK entities with a merger event in the last 90 days", "new LEIs issued in Luxembourg this week". The window applies to status_date, the date the current status took effect: LAPSED = the renewal date that was missed, RETIRED/ANNULLED = entity expiration date (else last update), ISSUED = initial registration, or to the event date when event_type is given. Returns total (exact up to 100,000) plus a page of rows, newest first, with data_as_of. Sole-proprietor names are withheld (personal data); call get_lei for one record.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since_days": 30,
      "jurisdiction": "DE",
      "registration_status": "LAPSED"
    },
    "name": "gleif_lei_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRows per page, 1-500 (default 100).
offsetNoRows to skip for paging (default 0).
categoryNoEntity category.
event_typeNoThe MOST RECENT legal-entity event recorded on the LEI (earlier events are not matched). When given, since_days applies to the event date instead of status_date. A merger shows up as RETIRED plus MERGERS_AND_ACQUISITIONS or ABSORPTION, and successor_lei names the survivor.
since_daysNoOnly entities whose status_date (or event date, with event_type) falls within the last N days, 1-3650.
jurisdictionYesLegal jurisdiction: ISO 3166-1 alpha-2 country ("DE", "GB", "US") or a subdivision ("US-DE", "CA-ON"). A country code includes its subdivisions. Common country names are converted.
entity_statusNoLegal entity status.
name_containsNoCase-insensitive fragment of the legal or other name, at least 3 characters, e.g. "bank".
registration_statusNoLEI registration status. LAPSED = renewal missed (the company may still exist); RETIRED = the entity ceased, including by merger (pair with event_type to tell which).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context beyond them: total exact only up to 100,000, rows returned newest-first, data_as_of, and sole-proprietor names withheld as personal data. It does not state rate limits or what happens when filters match nothing, so it stops short of the top mark.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core operation and scale, then filters, then semantics, then return shape — a sensible order. It runs long and repeats some schema wording, but every sentence carries operational information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, filter-heavy screening tool with no output schema, the description covers input semantics, the meaning of the time window, the return shape (total + page + data_as_of), and the one data-privacy caveat. An agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still earns credit by explaining the window's semantics — that since_days tracks status_date, what status_date means per status (LAPSED = missed renewal, RETIRED = entity expiration), and that event_type redirects the window to the event date. Much of this is mirrored in the schema text, so the added value is real but partly redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Bulk screen of LEI registrations") plus the exact scope (a jurisdiction across the ~3.4M-record GLEIF golden copy). It explicitly separates itself from the single-record sibling ("call get_lei for one record") so an agent can choose without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Four concrete example questions ("which LEIs in Germany lapsed in the last 30 days", "Delaware entities retired this quarter") map directly onto parameter combinations, making the use case unmistakable. It also names the alternative route for single-record lookups via get_lei, which is the main boundary an agent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.